Single-class support vector machine for an out-of-vocabulary rejection of isolated words

Author

He, Dongzhi ; Hou, Yibin ; Huang, Zhangqin ; Ding, Zhihao

Author_Institution

Inst. of Embedded Software & Syst., Beijing Univ. of Technol., Beijing, China

fYear

2009

Firstpage

1376

Lastpage

1380

Abstract

Single-class support vector machines (SC-SVMs) are different from the standard two-class SVM techniques. This algorithm is used to allow the pass through of the only positive data by treating the origin as the only member of the second class. Here, we present an algorithm for rejecting out-of-vocabulary (OOV) phrases. Our method uses SC-SVM mechanism to detect and reject the phrases of OOV. We also depict the trends in in-vocabulary (IV) correct recognition and OOV rejection with the number of command increasing and give an analysis.

Keywords

speech recognition; support vector machines; vocabulary; in-vocabulary correct recognition; out-of-vocabulary phrases rejection; single-class support vector machine; standard two-class SVM techniques; word speech recognition; Biomimetics; Educational programs; Educational technology; Embedded software; Helium; Laboratories; Robots; Speech recognition; Support vector machine classification; Support vector machines; OOV rejection; SC-SVM; speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Biomimetics (ROBIO), 2009 IEEE International Conference on

Conference_Location

Guilin

Print_ISBN

978-1-4244-4774-9

Electronic_ISBN

978-1-4244-4775-6

Type

conf

DOI

10.1109/ROBIO.2009.5420814

Filename

5420814